Lecture: 5.04.4012 Informationsverarbeitung und Kommunikation / Information Processing and Communication - Details

Lecture: 5.04.4012 Informationsverarbeitung und Kommunikation / Information Processing and Communication - Details

General information

Course name Lecture: 5.04.4012 Informationsverarbeitung und Kommunikation / Information Processing and Communication
Subtitle Schwerpunkt: Akustik und Signalverarbeitung
Course number 5.04.4012
Semester SoSe2024
Current number of participants 24
erwartete Teilnehmendenzahl 28
Home institute Institute of Physics
Courses type Lecture in category Teaching
First date Thu., 04.04.24, 10:00 - 12:00
Type/Form V
Pre-requisites Kenntnisse der Inhalte aus den Veranstaltungen Lineare Algebra, Mathematische Methoden der Physik, Messtechnik und Block-Praktikum Digitale Signalverarbeitung (FPR-B)
Performance record Exam or presentation or oral exam or homework or practical report
Lehrsprache englisch
ECTS points 6

Rooms and times

W32 1-113

  • Thursday, 10:00 - 12:00, Weekly (from 04.04.24)

W30 3-305

  • Wednesday, 14.08.24, 09:00 - 14:00 o'clock
  • Thursday, 15.08.24, 09:00 - 18:00 o'clock
  • Tuesday, 22.10.24, 09:00 - 16:00 o'clock
  • Wednesday, 23.10.24, 09:00 - 13:00 o'clock

Module assignments

Comment/Description

Course topics:
  • Information processing in the brain, neurons, receptive fields
  • Simple classification models, the perceptron, linear discriminant analysis, regression approach to classification
  • Generative approaches, k-nearest neighbour classification, Bayes equation
  • Model selection and cross-validation
  • Logistic regression, binary cross-entropy loss function, gradient descent
  • Gradient descent optimization and regularization, multi-layer perceptron and error backpropagation
  • Convolutional networks, deep neural networks, receptive fields in deep netoworks
  • Reinforcement learning
  • Sequence modeling, speech recognition, markov chains, hidden markov model (HMMs)
  • Transformer deep networks, large language models (LLMs), from HMMs to LLMs
  • Information theory, measuring information, entropy
  • Information theory continued, entropy bound for coding, compression

The course language is English or German, with English used by default and German used in case of only German native language speakers taking the course.

Admission settings

The course is part of admission "Anmeldung gesperrt (global)".
Erzeugt durch den Stud.IP-Support
The following rules apply for the admission:
  • Admission locked.